token-optimization · diff
git:20260424.1dd0635 to git:20261102.9100e69
1 added, 1 removed. Audit A to A.
---
description: Terse documentation mode — strip fluff from skill docs and agent prose
alwaysApply: true
---
- Skill docs and agent prose in this repo follow terse mode: drop articles, filler, hedging, preamble, and subject padding ("You should run" → "Run"). Keep technical terms exact, tables unchanged, numbered rules numbered, section headers for navigation. Strip code-block comments when surrounding prose already explains intent; keep comments on non-obvious behavior or in `assets/templates/`. Deduplicate format boilerplate (e.g. XAML `xmlns`) — include full once per file, then `<!-- standard xmlns omitted -->`.
+ Skill docs and agent prose in this repo follow terse mode: drop articles, filler, hedging, preamble, and subject padding ("You should run" → "Run"). Keep technical terms exact, including the terms other files or tests depend on; keep scope qualifiers and prohibitions ("only when…", "except…", "unless…", "never…"); keep tables unchanged, numbered rules numbered, section headers for navigation. State a repeated fact once in full and link to it from the others. Strip code-block comments when surrounding prose already explains intent; keep comments on non-obvious behavior or in `assets/templates/`. Deduplicate format boilerplate (e.g. XAML `xmlns`) — include full once per file, then `<!-- standard xmlns omitted -->`.
Full reference: `.claude/rules/token-optimization.md`.
Does NOT apply to: user-project code, CLI commands, YAML frontmatter, commit messages. Safety override for security warnings, irreversible actions, multi-step sequences.